scispace - formally typeset
Search or ask a question

Showing papers on "Periocular Region published in 2020"


Journal ArticleDOI
TL;DR: A novel method for person identification based on the fusion of iris and periocular biometrics has been proposed and the comparison with the state-of-the-art methods with respect to these databases shows the robustness and effectiveness of the proposed approach.

42 citations


Journal ArticleDOI
TL;DR: An identity-preserving synthetic ocular image generation mechanism that can be used for large scale data generation for training purposes or attack generation purposes is proposed and validated and the realistic image quality of generated images with high fidelity and identity preserving capabilities is established.

30 citations


Journal ArticleDOI
TL;DR: This is the first study to propose a detailed and standardized 3D anthropometric protocol for the periocular region and confirm its high precision and accuracy and provide novel metrical data concerning young CaucasianPeriocular anthropometry.
Abstract: Background The three-dimensional surface imaging system is becoming more common in plastic surgeries. However, few studies have assessed three-dimensional periocular structures and surgical outcomes. This study aimed to propose a standardized three-dimensional anthropometric protocol for the periocular region, investigate its precision and accuracy, and determine the three-dimensional periocular anthropometric norms for young Caucasians. Methods Thirty-nine healthy young Caucasians (78 eyes) were enrolled. Three-dimensional facial images were obtained with a VECTRA M3 stereophotogrammetry device. Thirty-eight measurements in periocular regions were obtained from these images. Every subject underwent facial surface capture twice to evaluate its precision. A paper ruler was applied to assess its accuracy. Results Sixty-three percent of measurements in linear distances, curvatures, angles, and indices were found to reach a statistically significant difference between sexes (p ≤ 0.05, respectively). Across all measurements, the average mean absolute difference was 0.29 mm in linear dimensions, 0.56 mm in curvatures, 1.67 degrees in angles, and 0.02 in indices. In relative error of magnitude, 18 percent of the measurements were determined excellent, 51 percent very good, 31 percent good, and none moderate. The mean value of the paper-ruler scale was 10.01 ± 0.05 mm, the mean absolute difference value 0.02 mm, and the relative error of magnitude 0.17 percent. Conclusions This is the first study to propose a detailed and standardized three-dimensional anthropometric protocol for the periocular region and confirm its high precision and accuracy. The results provided novel metric data concerning young Caucasian periocular anthropometry and determined the variability between sexes.

29 citations


Journal ArticleDOI
TL;DR: Stereophotograms obtained using caliper-derived direct anthropometry and 2-dimensional photogrammetry to 3D stereophotogrammetry yield very good reliability for a series of 2D and 3D measurements.
Abstract: Background Three-dimensional (3D) imaging has become increasingly popular in aesthetic surgery. However, few studies have emphasized its application in the periocular region. Objective To provide evidence supporting the reliability of generalizing periocular measurements obtained using caliper-derived direct anthropometry and 2-dimensional (2D) photogrammetry to 3D stereophotogrammetry. Materials and methods Periocular surfaces were captured using a stereophotogrammetry system for 46 normal Caucasian individuals. Twenty-two periocular variables were directly, 2-dimensionally, and 3-dimensionally measured. Reliability of these measurements was evaluated and compared with each other. Results The results revealed that, for direct (intra-rater reliability only), 2D, and 3D anthropometry, overall intra-rater and inter-rater intraclass correlation coefficient estimates were 0.88, 0.99 and 0.97, and 0.98 and 0.92, respectively; mean absolute differences were 0.84 mm, 0.26 and 0.36 units, and 0.35 and 0.67 units, respectively; technical error of measurement (TEM) estimates were 0.85 mm, 0.25 and 0.36 units, and 0.32 and 0.65 units, respectively; relative error measurement estimates were 6.46%, 1.69% and 2.74%, and 1.67% and 5.11%, respectively; and relative TEM estimates were 6.25%, 1.62% and 2.78%, and 2.12% and 5.12%, respectively. Conclusion Stereophotogrammetry and the authors' landmark location protocol yield very good reliability for a series of 2D and 3D measurements.

16 citations


Journal ArticleDOI
TL;DR: Ablation studies and experimental results on three publicly available cross-spectral periocular datasets containing images from VIS, near-infrared (NIR), and night vision domains show that the proposed deep network achieves the state-of-the-art recognition performances on all three datasets.

15 citations


Journal ArticleDOI
TL;DR: Seven different off-the-shelf deep learning based Convolutional Neural Networks using transfer learning approach are implemented on UBIPr database and experimental results demonstrated that for images with pose variation VGG 19 obtained maximum recognition accuracy while for matching of two different side of periocular region Res Net 18 outperform others.

15 citations


Journal ArticleDOI
TL;DR: The robustness of the proposed feature extraction is exemplified by comparing it with state-of-art approaches along with multiple deep networks where the improvement is evidently seen on large scale database with an average verification accuracy of Genuine Match Rate ≈ 98% at False Match Rate = 0.01%.

14 citations


Proceedings ArticleDOI
06 Jul 2020
TL;DR: This work presents and evaluates a fusion framework for improving the biometric authentication performance and employs score-level fusion for two independent biometric systems of iris and periocular region to avoid expensive feature- level fusion.
Abstract: The growing popularity of Virtual Reality and Augmented Reality (VR/AR) devices in many applications also demands authentication of users. As the devices inherently capture the eye image while capturing the user interaction, the authentication can be devised using the iris and periocular recognition. While both iris and periocular data being non-ideal unlike the data captured from standard biometric sensors, the authentication performance is expected to be lower. In this work, we present and evaluate a fusion framework for improving the biometric authentication performance. Specifically, we employ score-level fusion for two independent biometric systems of iris and periocular region to avoid expensive feature-level fusion. With a detailed evaluation of three different score-level fusion after the score normalization on a dataset of 12579 images, we report the performance gain in authentication using score-level fusion for iris and periocular recognition.

13 citations


Journal ArticleDOI
TL;DR: Books review of treatment options for basal cell carcinoma, which consist of surgery, or combined techniques plus vismodegib, radiotherapy and imiquimod, and functional and esthetic outcome in patients are important after clear excisions and reconstruction should be carefully considered.
Abstract: Basal cell carcinoma (BCC) as a non-melanoma skin cancer type is the most common malignant tumor throughout the world. The incidence is higher in age over 60. The intense of exposure to ultraviolet radiation is one of the known risk factors. Over 50% of BCC of the periocular region initially occur on the lower lid and inner angle. Literature review of treatment options for basal cell carcinoma, which consist of surgery, or combined techniques plus vismodegib, radiotherapy and imiquimod. The first consideration for treatment of periocular BCC is radical surgical excision using Mohs micrographic technique. Functional and esthetic outcome in patients are important after clear excisions and reconstruction should be carefully considered. Radical exenteration is considered in the case of orbital invasion of high-risk aggressive BCC.

13 citations


Journal ArticleDOI
TL;DR: It is found that good cosmetic and functional results can often be achieved with appropriate early intervention, but visual prognosis may remain guarded despite optimal treatment.

11 citations


Proceedings ArticleDOI
29 Apr 2020
TL;DR: A new normalization scheme to align the ocular images and then, a new reference sample selection protocol to achieve higher verification accuracy is proposed and is exemplified using two handcrafted feature extraction methods and two deep-learning strategies.
Abstract: Virtual and augmented reality technologies are increasingly used in a wide range of applications. Such technologies employ a Head Mounted Display (HMD) that typically includes an eye-facing camera and is used for eye tracking. As some of these applications require accessing or transmitting highly sensitive private information, a trusted verification of the operator’s identity is needed. We investigate the use of HMD-setup to perform verification of operator using periocular region captured from inbuilt camera. However, the uncontrolled nature of the periocular capture within the HMD results in images with a high variation in relative eye location and eye-opening due to varied interactions. Therefore, we propose a new normalization scheme to align the ocular images and then, a new reference sample selection protocol to achieve higher verification accuracy. The applicability of our proposed scheme is exemplified using two handcrafted feature extraction methods and two deep-learning strategies. We conclude by stating the feasibility of such a verification approach despite the uncontrolled nature of the captured ocular images, especially when proper alignment and sample selection strategy is employed.

Journal ArticleDOI
03 May 2020-Orbit
TL;DR: One of the largest ever case series of this uncommon lesion occurring in the periocular region is described and its clinical features, imaging characteristics, and surgical management are discussed.
Abstract: Intravascular papillary endothelial hyperplasia (IPEH) is a benign vascular lesion, typically found in the skin, consisting of a papillary proliferation of endothelial cells intimately related to a thrombus; it appears to be a rare variant of an organizing process. IPEH very rarely develops in the periocular region, with fewer than 20 such cases currently reported in the English language literature. We describe one of the largest ever case series of this uncommon lesion occurring in the periocular region and discuss its clinical features, imaging characteristics, and surgical management.

Journal ArticleDOI
TL;DR: The periocular region sees high rates of cancer compared to the rest of the body and can be affected by several unique tumors, although adjunctive therapies and prognosis vary depending on the diagnosis.
Abstract: The periocular region sees high rates of cancer compared to the rest of the body and can be affected by several unique tumors Treatment typically involves surgical excision, although adjunctive therapies and prognosis vary depending on the diagnosis Basal cell carcinoma (BCC) is the most common malignancy affecting this region and should be excised promptly This is followed by squamous cell carcinoma, which is often mistaken for BCC but is treated similarly Melanoma is less common but more deadly, with relatively high rates of metastasis and death Rare tumors that may be found in this region include sebaceous carcinoma, Merkel cell carcinoma, and microcystic adnexal carcinoma While uncommon, these tumors are associated with poor outcomes and frequent recurrence Recognition of periocular skin cancer is an important skill for primary care physicians, as prompt diagnosis and treatment can be sight or life-saving

Posted Content
TL;DR: A new periocular dataset containing samples from 1,122 subjects, acquired in 3 sessions by 196 different mobile devices is presented, and an extensive benchmark with several Convolutional Neural Network architectures and models that have been employed in state-of-the-art approaches based on Multi-class Classification, Multitask Learning, Pairwise Filters Network, and Siamese Network is performed.
Abstract: Recently, ocular biometrics in unconstrained environments using images obtained at visible wavelength have gained the researchers' attention, especially with images captured by mobile devices. Periocular recognition has been demonstrated to be an alternative when the iris trait is not available due to occlusions or low image resolution. However, the periocular trait does not have the high uniqueness presented in the iris trait. Thus, the use of datasets containing many subjects is essential to assess biometric systems' capacity to extract discriminating information from the periocular region. Also, to address the within-class variability caused by lighting and attributes in the periocular region, it is of paramount importance to use datasets with images of the same subject captured in distinct sessions. As the datasets available in the literature do not present all these factors, in this work, we present a new periocular dataset containing samples from 1,122 subjects, acquired in 3 sessions by 196 different mobile devices. The images were captured under unconstrained environments with just a single instruction to the participants: to place their eyes on a region of interest. We also performed an extensive benchmark with several Convolutional Neural Network (CNN) architectures and models that have been employed in state-of-the-art approaches based on Multi-class Classification, Multitask Learning, Pairwise Filters Network, and Siamese Network. The results achieved in the closed- and open-world protocol, considering the identification and verification tasks, show that this area still needs research and development.

Journal ArticleDOI
TL;DR: Free skin grafts in the periocular area are fully reperfused after 7 weeks, and this area is known to be well-vascularized and thus forgiving to reconstructive surgery.
Abstract: PURPOSE: Free skin grafts are frequently used in reconstructive surgery. However, little is known about the course of reperfusion due to the previous lack of reliable perfusion monitoring techniques. The aim of this study was to use state-of-the-art laser speckle contrast imaging to monitor free skin grafts in the periocular area.METHODS: Seven patients needing surgery due to tumor removal or cicatricial ectropion in the periocular region underwent reconstructive surgery using free skin grafts from either the contralateral upper eyelid or the upper inner arm. The free skin grafts measured 10-30 mm horizontally and 9-30 mm vertically. Blood perfusion was monitored using laser speckle contrast imaging immediately postoperatively (0 weeks) and at follow-up after 1, 3, and 7 weeks.RESULTS: All grafts were reperfused gradually during healing, the median value being 46% in the central part of the graft after 1 week and 79% after 3 weeks. The grafts were completely reperfused after 7 weeks. No difference was observed in the rate of reperfusion between the center and periphery of the grafts (p = not significant). The cosmetic and functional outcome was excellent in all but 1 patient, who developed ectropion that had to be surgically corrected.CONCLUSIONS: Skin grafts in the periorbital area are fully reperfused after 7 weeks. The periocular area is known to be well-vascularized and thus forgiving to reconstructive surgery. Future investigations of the reperfusion of free skin grafts in other parts of the body or in higher-risk populations should be carried out.

Proceedings ArticleDOI
01 Aug 2020
TL;DR: This work explores a complementary approach to biometric face recognition, that is the dynamics of facial landmark during phonation while pronouncing sentences, which can be seen as a kind of signature that uniquely and unmistakably identifies an individual.
Abstract: Face identification is one of the most widely adopted approach in several real scenarios. Unfortunately, in presence of occlusions or non-cooperative subjects nontrivial issues arise. This work explores a complementary approach to biometric face recognition, that is the dynamics of facial landmark during phonation while pronouncing sentences. These dynamics (both periocular and labial area) can be seen as a kind of signature that uniquely and unmistakably identifies an individual. The experimental results focus the attention on periocular area, which represents one of the most discriminating physiological characteristics after the whole face. Preliminary experimental results conducted on a public dataset and considering 14 periocular features showed an accuracy slightly below 80%, which confirms the robustness in uncontrolled scenarios.

Book ChapterDOI
30 Jul 2020
TL;DR: The results of this work may serve as inputs for ensemble emotion recognition systems, and also as guidelines for enhancing works involving periocular-feature-based Facial Emotion Recognition systems.
Abstract: Image processing and Machine Learning approaches are used for face detection and emotion recognition There are many features that could be extracted from a facial image, but the focus of this work is on identifying emotions by analyzing the features in the periocular region of the face; the region that consists of the features lying in the area of the immediate vicinity of the eyes The work is broadly divided into two major modules: facial feature extraction and selection, and classifier training and evaluation 327 labeled images are used to select seven features (periocular action units) Five classifiers are tested, and the Random Forest classifier provided the highest prediction accuracy at 7561%, with the best performance observed for the happiness emotion label The k-Nearest Neighbor classifier follows with a performance of 72% when augmented with Neighborhood Components Analysis Statistical tests confirm that there is a significant difference between the performance of Random Forest classifier and SVM The results of this work may serve as inputs for ensemble emotion recognition systems, and also as guidelines for enhancing works involving periocular-feature-based Facial Emotion Recognition systems

Journal Article
TL;DR: EndyMED 3DEEP in combination with FSR appears to be safe and effective in treating periocular skin aging.
Abstract: BACKGROUND: The early signs of skin aging usually occur in the periocular region. OBJECTIVES: This retrospective analysis evaluated the efficacy and safety profile of a multisource 3DEEP radiofrequency (RF) technology (EndyMed, Caesarea, Israel) in combination with fractional skin resurfacing (FSR) for the treatment of periocular skin aging. METHODS: A total of 15 patients with periocular aging underwent monthly treatment sessions of 3DEEP and FSR for three months. Sessions were administered at the Department of Dermatology at Xijing Hospital in Xi'an, China. Indices of skin moisture level, transepidermal water loss (TEWL), skin elasticity, wrinkles, pore size, and skin texture were determined before and after treatment using the Visia® (Canfield Imaging Systems, New Jersey), Multiprobe Adapter (CK, Cologne, Germany) and Antera3D® (Miravex, Dublin, Ireland) systems. RESULTS: Skin moisture level, elasticity, wrinkles, pore size, and texture improved relative to baseline (p 0.05). Patient satisfaction was 86.67 percent. Patients experienced varying degrees of transient edema, erythema, scabbing, and occasional hyperpigmentation; all adverse effects resolved within 2 to 10 days post-treatment. CONCLUSION: ENDYMED 3DEEP in combination with FSR appears to be safe and effective in treating periocular skin aging. Randomized controlled trials with a larger patient group are needed to confirm our findings.

Journal ArticleDOI
TL;DR: Submental and anterior neck regions are useful full-thickness skin graft donor sites for eyelids procedures, particularly in elderly females with submental fullness and skin redundancy, and can be considered whenever traditional donor sites are unavailable.
Abstract: Purpose The submental and neck regions share cutaneous features with the face and are suitable donor sites for facial full-thickness skin grafts (FTSGs). Age-related laxity and skin redundancy in the cervicomental region may be an additional motivator to use its skin. We aim to describe, raise awareness, and remind surgeons of the utilization of submental and anterior neck as sources of FTSG for the periocular region, particularly when traditional donor sites are unavailable. Methods Retrospective case series of 5 patients who underwent periocular FTSG from anterior neck and submental regions between January 2017 and January 2019. All patients had contraindications to the usually preferred graft donor sites. Main outcome measures were surgical functional results and cosmesis. Results Five patients (all female) received FTSGs using anterior neck and submental regions as donor sites. Two patients required skin grafts due to eyelid retraction and anterior lamella shortening; one due to previous multiple basal cell carcinoma excisions with FTSG reconstructions and the other due to chronic Bell's palsy. Three patients required skin grafts for Hughes flap reconstruction after excision of lower eyelid basal cell carcinoma. In all patients, conventional skin donor sites were unavailable or unsuitable due to previous skin grafting, actinic changes, postauricular situated hearing aids or patient's preference. All patients achieved good cosmesis and functional results. None of the patients experienced donor site morbidities. Conclusions Submental and anterior neck regions are useful FTSG donor sites for periocular procedures, particularly in elderly female patients with submental fullness and neck skin redundancy.

Journal ArticleDOI
TL;DR: The rationale to further investigate avelumab as a potential therapy for advanced or metastatic eyelid and periocular MCC is provided and the efficacy of two other immune checkpoint inhibitors are described.
Abstract: Merkel cell carcinoma (MCC) is a highly aggressive cutaneous malignancy, with a high metastasis rate and a significant proportion of cases affecting the eyelid or periocular region. Current treatments for periocular MCC include wide local excision (WLE) with or without adjuvant radiotherapy and can result in profound morbidity and visual deficit. Metastatic disease has been traditionally treated with chemotherapy, though durable responses are typically poor and toxicity is high. Avelumab (Bavencio®, Merck KgaA, Darmstadt, Germany and Pfizer Inc., New York, NY, USA), the first FDA-approved human anti-programmed death-ligand 1 (PD-L1) antibody for the treatment of metastatic MCC (mMCC), has demonstrated safety and efficacy as first-line treatment and in chemotherapy-refractory cases. This review summarizes pivotal clinical trial data for avelumab in the treatment of mMCC, including efficacy, safety and tolerability, and describes the efficacy of two other immune checkpoint inhibitors, pembrolizumab (Keytruda®, Merck & Co., Inc., Kenilworth, NJ, USA) and nivolumab (Opdivo®, Bristol‐Myers Squibb, New York, NY, USA and Ono Pharmaceuticals, Trenton, NJ, USA) for the treatment of advanced MCC. Our purpose is to provide the rationale to further investigate avelumab as a potential therapy for advanced or metastatic eyelid and periocular MCC.


Book ChapterDOI
24 Nov 2020
TL;DR: Facial images covered with mask can still be used for the authentication using face recognition at a nearly same level of accuracy, which means that people can use the face recognition applications without taking off the mask, which provides the safe circumstances against the infections.
Abstract: Due to COVID-19 pandemic, wearing a mask rapidly becomes a new social norm that people in the society should comply Although it is altruistic behavior preventing all people from serious infections, it brings about hassles for individuals For example, when a face is partly covered with a mask, identification using a face recognition is going to be malfunctioning To this end, we propose a novel computational framework that enables the personal authentication with a partial face image, a face covered with a mask For the experiments, we constructed the datasets of facial images containing the periocular regions only, extracted from full facial images covered with the mask Given the datasets, we trained our framework, a variant of a Siamese network, with various configuration of hyper-parameters As a result, RMSprop optimizer with the learning rate 1 \(\times \) 10–5 trained from periocular datasets showed the highest accuracy for the personal authentication Next, we conducted a comparative experiment with our proposal and the model trained with datasets containing the full facial regions When testing with the periocular region images, our proposal is superior in the authentication accuracy to that of the model trained with the full facial regions This result raises the optimistic expectation that in the era of COVID-19, facial images covered with mask can still be used for the authentication using face recognition at a nearly same level of accuracy This means that people can use the face recognition applications without taking off the mask, which provides the safe circumstances against the infections

Book ChapterDOI
18 Nov 2020
TL;DR: This work describes the use of convolutional neural network Neocognitron, in this novel application, in individual recognition using periocular region images, and the competitive learning using the extreme points of lines detected in the preprocessing of the input images as winner positions.
Abstract: There are some benefits in using periocular biometric traits for individual identification. This work describes the use of convolutional neural network Neocognitron, in this novel application, in individual recognition using periocular region images. Besides, it is used the competitive learning using the extreme points of lines detected in the preprocessing of the input images as winner positions. It was used Carnegie Mellon University - Pose, Illumination, and Expression Database (CMU-PIE), with 41,368 images of 68 persons. From these images, 57 \(\times \) 57 periocular images were obtained as training and test samples. The experiments indicate results in the Kappa index of 0.89, for periocular images, and 0.91 for complete face images.

Patent
24 Mar 2020
TL;DR: In this paper, a composition for cleaning eyelids or periocular regions, and a pad comprising the same, is presented to protect the skin from external stimulation elements, and prevent blepharitis, Demodex, etc.
Abstract: The present invention relates to a composition for cleaning eyelids or periocular regions, and a pad comprising the same. The present invention can be used to remove deposited wastes from eyelids and periocular regions, protect the skin from external stimulation elements, and prevent blepharitis, Demodex, etc., and the pad comprising the composition for cleaning eyelids or periocular regions is easy to use because only necessary parts can be wiped without the need for separate cleaning.


Book ChapterDOI
01 Jan 2020
TL;DR: This chapter will review the various treatment modalities and special considerations for the periocular BCC.
Abstract: Basal cell carcinoma (BCC) of the periocular region presents unique challenges owing to the unique anatomic and functional implications of proximity of the cancer to the eye and the potential negative impact of treatments on both the visual function and aesthetic outcomes. This chapter will review the various treatment modalities and special considerations for the periocular BCC.

Book ChapterDOI
Craig N. Czyz1
01 Jan 2020
TL;DR: The periocular region has a robust, highly anastomotic vascular supply that allows for a reduced infection rate compared to other surgical sites as mentioned in this paper, but serious infections can occur involving atypical mycobacteria, Staphylococcus aureus, and group A β-hemolytic Streptococcus necrotizing fasciitis.
Abstract: The periocular region has a robust, highly anastomotic vascular supply that allows for a reduced infection rate compared to other surgical sites. The National Nosocomial Infections Surveillance system reported a postoperative infection rate of approximately 2% for all types of surgery. In contrast, studies of common periocular procedures place the infection rate between 0.02% and 0.4%. Despite these favorable statistics, serious infections can occur involving atypical mycobacteria, Staphylococcus aureus, and group A β-hemolytic Streptococcus necrotizing fasciitis.

Journal ArticleDOI
08 Dec 2020-Orbit
TL;DR: The clinical features and outcomes in three cases of pleomorphic adenoma with two at the medial canthus (including one recurrence) and one in the brow region are described.
Abstract: Mixed tumour of the skin is a rare entity also known as chondroid syringoma and pleomorphic adenoma. These usually present as slow-growing skin nodules with a smooth surface, clear boundaries, and no ulceration. Case series exist describing pleomorphic adenomas in the periocular region including the lids and orbit, separate to the more familiar lacrimal gland pleomorphic adenoma. These may arise from accessory or ectopic lacrimal gland tissue but in the eyelids are more likely to arise from sweat glands in the skin. Histopathological analysis of these lesions is important to identify complete excision, minimising recurrences and in identifying rare but potential malignant transformation. We describe the clinical features and outcomes in three cases of pleomorphic adenoma with two at the medial canthus (including one recurrence) and one in the brow region.

Book ChapterDOI
01 Jan 2020
TL;DR: An understanding of the anatomy of the eye, orbit, eyelid, nasolacrimal system and periocular region is essential when considering a wide variety of disease that presents to the ophthalmic clinician.
Abstract: An understanding of the anatomy of the eye, orbit, eyelid, nasolacrimal system and periocular region is essential when considering the wide variety of disease that presents to the ophthalmic clinician.

Journal Article
TL;DR: This project proposes a novel approach to efficiently extract discriminative properties of the periocular region with high recognition performance and uses Harlick features and edge histogram descriptor to extract the features of training images.
Abstract: Periocular recognition has been an active research area in the field of biometrics. The periocular region is normally a rectangular region localized by the eye center or the inner and outer corners of the eye. Choosing features that represent the reliable and discriminative properties of the periocular region is one of the most critical tasks in the periocular recognition problem. This project tackles this feature extraction problem and proposes a novel approach to efficiently extract discriminative properties of the periocular region with high recognition performance. The proficiency to learn robust features from the images makes the Bayesian support vector machine (BSVM) attractive for recognition. Harlick features and edge histogram descriptor is used to extract the features of training images.